Proceedings Article10.1109/IWFHR.2004.93
Self-supervised adaptation for on-line text recognition
Loïc Oudot,L. Prevost,A. Moises +2 more
- 26 Oct 2004
- pp 9-13
TL;DR: This paper develops a handwritten text recognizer for on-line text written on a touch-terminal based on the activation-verification cognitive model and presents several strategies of self-supervised writer-adaptation that are compared to the supervised adaptation scheme.
read more
Abstract: We developed a handwritten text recognizer for on-line text written on a touch-terminal. This system is based on the activation-verification cognitive model. It is composed of three experts dedicated respectively to signal segmentation in symbols, symbol classification and lexical analysis of the classification results. The baseline system is writer-independent. We present in this paper several strategies of self-supervised writer-adaptation that we compare to the supervised adaptation scheme. The best strategy called "prototype dynamic management" modifies the recognizer parameters allowing to get results close to the supervised methods. Results are presented on a 90 texts (5400 words) database written by 38 different writers.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
An activation-verification model for on-line texts recognition
Loïc Oudot,L. Prevost,M. Milgram +2 more
- 26 Oct 2004
TL;DR: A new writer-independent system dedicated to the automatic recognition of on-line texts using a very large French lexicon which cover a vast field of application.
Patent
Apparatus, method, non-transitory computer-readable medium and system
Hiroaki Ogawa
- 15 Jul 2015
TL;DR: In this article, an apparatus including a communication unit configured to transmit information permitting a second apparatus to modify stored voice recognition information based on a relationship between the first apparatus and the second apparatus.
12
New Advances and New Challenges in On-Line Handwriting Recognition and Electronic Ink Management
Eric Anquetil,Guy Lorette +1 more
- 01 Jan 2007
TL;DR: The main goal of this chapter is to make an overview of new advances in on-line handwriting recognition systems, electronic ink management systems, open problems, new challenges and new perspectives.
10
Hybrid generative/discriminative classifier for unconstrained character recognition
Lionel Prevost,Loïc Oudot,A. Moises,Christian Michel-Sendis,Maurice Milgram +4 more
- 01 Sep 2005
TL;DR: This paper presents an original two stages recognizer which is a model-based classifier which store an exhaustive set of character models and a pairwise classifiers which separate the most ambiguous pairs of classes.
References
An activation--verification model for letter and word recognition: the word-superiority effect
TL;DR: An activation-verification model for letter and word recognition yielded predictions of two-alternative forced-choice performance for 864 individual stimuli that were either words, orthographically regular nonwords, or orthographically irregular nonwords.
567
Writer adaptation for online handwriting recognition
S.D. Connell,Anil K. Jain +1 more
TL;DR: This work uses writer-independent writing style models (lexemes) to identify the styles present in a particular writer's training data and updates these models using the writer's data, demonstrating the feasibility of this approach on both isolated handwritten character recognition and unconstrained word recognition tasks.
98
Comparing adaptation techniques for on-line handwriting recognition
A. Brakensiek,A. Kosmala,Gerhard Rigoll +2 more
- 10 Sep 2001
TL;DR: An online handwriting recognition system with focus on adaptation techniques that can be adapted to the writing style of a new writer using either a retraining depending on the EM (expectation maximization)-approach or an adaptation according to the MAP or MLLR (maximum likelihood linear regression)-criterion.
36
Writer adaptation of online handwriting models
S.D. Connell,N.K. Jain +1 more
- 20 Sep 1999
TL;DR: The approach to writer-adaptation makes use of writer-independent writing style models (called lexemes), to identify the styles present in a particular writer's training data, which are then retrained using the writer's data.
31
•Proceedings Article
A Constructive RBF Network for Writer Adaptation
John Platt,Nada Matic +1 more
- 03 Dec 1996
TL;DR: A fairly general adaptation algorithm which augments a standard neural network to increase its recognition accuracy for a specific user by using an Output Adaptation Module which maps this output into the correct user-dependent confidence vector.